From: Bharata B Rao <bharata@amd.com>
To: Vinay Banakar <vny@google.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: akpm@linux-foundation.org, willy@infradead.org, mgorman@suse.de,
Wei Xu <weixugc@google.com>, Greg Thelen <gthelen@google.com>
Subject: Re: [PATCH] mm: Optimize TLB flushes during page reclaim
Date: Wed, 22 Jan 2025 14:29:19 +0530 [thread overview]
Message-ID: <9e0fc33a-2e2b-4366-ae1b-231038dfd2be@amd.com> (raw)
In-Reply-To: <CALf+9Yeq+FCeWW29Mradv1NnhkCyLQi_vVkzKY9-z24nZgw64w@mail.gmail.com>
On 21-Jan-25 5:35 AM, Vinay Banakar wrote:
> Sorry, the previous patch was unreadable due to damaged whitespace.
> Here is the same patch with fixed indentation.
>
> Signed-off-by: Vinay Banakar <vny@google.com>
> ---
> mm/vmscan.c | 107
> ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---------------------------------
> 1 file changed, 74 insertions(+), 33 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index bd489c1af..1bd510622 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1035,6 +1035,7 @@ static unsigned int shrink_folio_list(struct
> list_head *folio_list,
> struct folio_batch free_folios;
> LIST_HEAD(ret_folios);
> LIST_HEAD(demote_folios);
> + LIST_HEAD(pageout_list);
> unsigned int nr_reclaimed = 0;
> unsigned int pgactivate = 0;
> bool do_demote_pass;
> @@ -1351,39 +1352,9 @@ static unsigned int shrink_folio_list(struct
> list_head *folio_list,
> if (!sc->may_writepage)
> goto keep_locked;
>
> - /*
> - * Folio is dirty. Flush the TLB if a writable entry
> - * potentially exists to avoid CPU writes after I/O
> - * starts and then write it out here.
> - */
> - try_to_unmap_flush_dirty();
> - switch (pageout(folio, mapping, &plug)) {
> - case PAGE_KEEP:
> - goto keep_locked;
> - case PAGE_ACTIVATE:
> - goto activate_locked;
> - case PAGE_SUCCESS:
> - stat->nr_pageout += nr_pages;
> -
> - if (folio_test_writeback(folio))
> - goto keep;
> - if (folio_test_dirty(folio))
> - goto keep;
> -
> - /*
> - * A synchronous write - probably a ramdisk. Go
> - * ahead and try to reclaim the folio.
> - */
> - if (!folio_trylock(folio))
> - goto keep;
> - if (folio_test_dirty(folio) ||
> - folio_test_writeback(folio))
> - goto keep_locked;
> - mapping = folio_mapping(folio);
> - fallthrough;
> - case PAGE_CLEAN:
> - ; /* try to free the folio below */
> - }
> + /* Add to pageout list for defered bio submissions */
> + list_add(&folio->lru, &pageout_list);
> + continue;
The dirty pages are collected in a list here...
> }
>
> /*
> @@ -1494,6 +1465,76 @@ static unsigned int shrink_folio_list(struct
> list_head *folio_list,
> }
> /* 'folio_list' is always empty here */
>
> + if (!list_empty(&pageout_list)) {
> + /*
> + * Batch TLB flushes by flushing once before processing
> all dirty pages.
> + * Since we operate on one PMD at a time, this batches
> TLB flushes at
> + * PMD granularity rather than per-page, reducing IPIs.
> + */
> + struct address_space *mapping;
> + try_to_unmap_flush_dirty();
and one flush request is issued for the entire list. Where is the PMD
level (512) batching done? Is that implicit elsewhere in the flow?
> +
> + while (!list_empty(&pageout_list)) {
> + struct folio *folio = lru_to_folio(&pageout_list);
> + list_del(&folio->lru);
> +
> + /* Recheck if page got reactivated */
> + if (folio_test_active(folio) ||
> + (folio_mapped(folio) && folio_test_young(folio)))
> + goto skip_pageout_locked;
> +
> + mapping = folio_mapping(folio);
> + pageout_t pageout_res = pageout(folio, mapping, &plug);
> + switch (pageout_res) {
> + case PAGE_KEEP:
> + goto skip_pageout_locked;
> + case PAGE_ACTIVATE:
> + goto skip_pageout_locked;
> + case PAGE_SUCCESS:
> + stat->nr_pageout += folio_nr_pages(folio);
> +
> + if (folio_test_writeback(folio) ||
> + folio_test_dirty(folio))
> + goto skip_pageout;
> +
> + /*
> + * A synchronous write - probably a ramdisk. Go
> + * ahead and try to reclaim the folio.
> + */
> + if (!folio_trylock(folio))
> + goto skip_pageout;
> + if (folio_test_dirty(folio) ||
> + folio_test_writeback(folio))
> + goto skip_pageout_locked;
> +
> + // Try to free the page
> + if (!mapping ||
> + !__remove_mapping(mapping, folio, true,
> + sc->target_mem_cgroup))
> + goto skip_pageout_locked;
> +
> + nr_reclaimed += folio_nr_pages(folio);
> + folio_unlock(folio);
> + continue;
> +
> + case PAGE_CLEAN:
> + if (!mapping ||
> + !__remove_mapping(mapping, folio, true,
> + sc->target_mem_cgroup))
> + goto skip_pageout_locked;
> +
> + nr_reclaimed += folio_nr_pages(folio);
> + folio_unlock(folio);
> + continue;
> + }
> +
> +skip_pageout_locked:
> + folio_unlock(folio);
> +skip_pageout:
> + list_add(&folio->lru, &ret_folios);
> + }
> + }
> +
> /* Migrate folios selected for demotion */
> nr_reclaimed += demote_folio_list(&demote_folios, pgdat);
> /* Folios that could not be demoted are still in @demote_folios */
Regards,
Bharata.
next prev parent reply other threads:[~2025-01-22 8:59 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-01-20 22:47 [PATCH] mm: Optimize TLB flushes during page reclaim Vinay Banakar
2025-01-21 0:05 ` Vinay Banakar
2025-01-22 8:59 ` Bharata B Rao [this message]
2025-01-22 11:09 ` Vinay Banakar
2025-01-22 11:31 ` Bharata B Rao
2025-01-22 13:28 ` Vinay Banakar
2025-01-22 20:05 ` SeongJae Park
2025-01-23 17:11 ` Vinay Banakar
2025-01-23 17:23 ` SeongJae Park
2025-01-23 18:17 ` Matthew Wilcox
2025-01-21 1:43 ` Byungchul Park
2025-01-21 18:03 ` Vinay Banakar
2025-01-23 4:17 ` Rik van Riel
2025-01-23 19:16 ` Vinay Banakar
2025-01-28 22:01 ` Rik van Riel
2025-03-17 19:20 ` Rik van Riel
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=9e0fc33a-2e2b-4366-ae1b-231038dfd2be@amd.com \
--to=bharata@amd.com \
--cc=akpm@linux-foundation.org \
--cc=gthelen@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=vny@google.com \
--cc=weixugc@google.com \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).